KPM Analytics has unveiled an AI-powered robotic potato sorter designed to automate the final inspection process, aiming to enhance grading accuracy and reduce operational costs for fresh-pack potato processors. It comes at a time when the industry is struggling to find workers, according to the company.
The SiftAI Robotic Sorter, developed by Smart Vision Works, a KPM Analytics brand, combines a delta robot with an AI-based vision inspection system programmed to detect potato size, shape, and defects such as bruises, cracks, and green discolouration. Installed over a roller table, the system captures images of all sides of each potato. Potatoes that fall outside the AI model’s acceptance criteria are removed from the product stream by the robotic arm at rates of 80 to 100 picks per minute in two-robot configurations.
“Because of potato oversupply and rising wages in North America, many potato processors are losing money on every box shipped,” said Curtis Koelling, vice-president of product development and innovation for Smart Vision Works. “Managers are eager to identify technology that can lower their production costs. When they see a competitor managing final inspection without labour costs, they become very interested in the technology,” he said.
According to KPM Analytics, human inspectors typically discard 10 to 20 per cent of acceptable potatoes, reducing profits, while aiming to meet industry standards of no more than five per cent defective potatoes reaching customers, as set by the U.S. Department of Agriculture. In beta testing, the SiftAI Robotic Sorter reportedly reduced the percentage of missed defects and misgraded potatoes.
The company states that the investment in the robotic sorter can pay for itself in fewer than two years when considering increased profitability alongside labour savings.
The SiftAI Robotic Sorter is now available for order, including a vision-based inspection system, AI software, and a potato-inspection model comprising 19 different defects.
KPM Analytics is a provider of scientific instrumentation focused on analysing critical parameters within the food, feed, agriculture, and environmental sectors.